Knowledge Base Feedback
Definition
Knowledge base feedback is a systematic process for collecting user assessments of help content quality and usefulness. The most common feedback mechanisms are binary ratings (thumbs up/down, helpful/not helpful), star ratings, and free-text comment fields. Advanced feedback systems also capture implicit signals such as whether a user submitted a support ticket immediately after reading an article (a strong negative signal) or whether they successfully completed the related task. Feedback data is used by content teams to prioritize article improvements, identify content gaps, and measure the overall health of the knowledge base.
Why It Matters
Without feedback, knowledge base content teams are operating blind — they publish articles without knowing whether they actually help users. Feedback mechanisms close the loop between content creation and user outcome. Articles with consistently low ratings signal content problems: unclear writing, outdated information, missing steps, or wrong context. High-rated articles can be promoted in search results and suggested more prominently. For AI chatbots, tracking whether users rate responses positively after the bot retrieved a specific article helps optimize knowledge retrieval and identify content that needs updating.
How It Works
Knowledge base feedback is implemented at the article level with simple UI elements (typically at the bottom of articles) asking 'Was this article helpful?' followed by a yes/no button. When users select 'no', they are often prompted for more detail: 'What was missing?' or 'Was this information inaccurate?'. Feedback data is aggregated in the knowledge base analytics dashboard, where content managers can sort articles by rating, filter for low-rated content, and assign review tasks. Some platforms also track feedback patterns over time to detect when articles degrade as the product evolves.
Feedback Collection & Improvement Loop
82%
Helpful
18%
Not Helpful
34%
With Comment
Real-World Example
A 99helpers customer discovers that their 'Setting Up Integrations' article has a 28% positive rating — much lower than the 72% average across their knowledge base. After examining the 'no' feedback comments, they find that users are confused by step 4, which assumes knowledge of an API key location that was moved in a recent product update. They update the article with a new screenshot and clearer instructions. The article's rating improves to 68% within two weeks.
Common Mistakes
- ✕Collecting feedback but not acting on it — feedback data only has value if it drives content improvement actions
- ✕Using only binary yes/no ratings without qualitative follow-up — binary ratings tell you there is a problem but not why
- ✕Measuring feedback rates instead of feedback ratios — a 100% response rate on negative feedback is worse than a 10% response rate on positive feedback
Related Terms
Knowledge Base Analytics
Knowledge base analytics tracks how users and AI systems interact with knowledge base content — measuring article views, search queries, resolution rates, feedback ratings, and content gaps. These insights drive continuous improvement of both the content and the AI chatbot powered by it.
Article Rating
Article rating is the mechanism that allows users to evaluate the quality and helpfulness of individual knowledge base articles, typically using thumbs up/down votes or star ratings.
Content Gap Analysis
Content gap analysis is a systematic review of what topics a knowledge base covers versus what users are actually asking — identifying areas where content is missing, insufficient, or outdated. It combines analytics data, chatbot logs, and user feedback to prioritize new content creation.
Zero-Results Rate
Zero-results rate is the percentage of knowledge base searches or AI retrieval queries that return no relevant results. It is a direct measure of knowledge gaps — every zero-results query represents a user question that the knowledge base cannot answer and a specific, actionable opportunity to create new content.
Knowledge Base Optimization
Knowledge base optimization is the ongoing process of improving a knowledge base's content quality, structure, and coverage to maximize AI chatbot accuracy and user self-service success rates. It involves analyzing search failures, filling content gaps, improving article clarity, and retiring outdated content.
Ready to build your AI chatbot?
Put these concepts into practice with 99helpers — no code required.
Start free trial →